I left tmux+vscode a few months ago and haven’t looked back. Clearly this new thing is better than flipping between a dozen tmux panes and other windows.
But I’m using my own “IDE” inspired by herdr and pane, worktrees down the left and panes on the right, but besides terminals the types of panes also include:
- A native Obsidian-level markdown editor with support for comments that agents can see
- Claude code with chrome for context size, and a custom UI that looks more like the web
- A diff viewer with support for comments
- A browser
- Can tag worktrees with PRs and issues
- Everything (except the browser) works seamlessly over ssh
It’s all zig+gtk, all vibe coded. I rarely open vscode these days.
Maybe the herdr plugin ecosystem can support all this too. I kinda want to get out of the business of hand-polishing UI.
I actually did the same but at some point was like "this is good enough" and it works well. Diffs, comments on diffs, integration with Linear and worktrees is good enough for now and gives me a productivity boost. Couple of other apps in the space but at the time none supported Claude Code in terminals
You certainly can do this for code, and it’ll give you great answers. But I find that, for whatever reason, info that I consume this way has a much shorter TTL in my brain than something I wrote myself.
I’ve been experimenting with writing a living spec — API endpoints, schemas, how things work at a low enough level that the LLM can fill in the details - and that’s been working well.
It also forces me to do the hammock-driven development necessary to build the right thing, and as a byproduct it keeps the design in my head longer.
I think over time our memory is worse than we think it is and writing things down is good for your own function as well as human groups you work with and AI. Like I do not care a lot for the AGENTS.md but if there is a certain kind of task like “write a test which mocks things in a certain way” or “implement a DAO object” it is very much worth picking one as a case study and adding a lot of inline comments that explain theory or reasoning or the steps involved in doing something and when you want it to write something say “take a look at A as an example, but I know there will be these differences…” and the same is good for you siz months later or another team member.
Doing sports ohotography I might got to a certain indoor track meet once a year and there is a lot to know about the order of events and how to move around in the space and where the good backgrounds are that I will have to rediscover unless I write a “runbook” which again lets me share that knowledge.
A coven has a “book of shadows” and for me it is mostly a runbook, like there are a lot of ways you can cast a circle and I like some liturgy better than others so if you get consensus on things you can write it down, even the Greeks thought writing things down impaired your ability to remember things but it’s easier to stay consistent and you do memorize it over time though…. It is annoying that a lot of people are reading off their phones in ritual spaces.
What stack do you use for that home inference? I’m rolling my own with gemma4, but even with Claude helping with the implementation it’s a lot of moving pieces to figure out.
Ollama serves models on an OpenAI compatible API directly on the inference machine, which most open source harness software will connect to. The inference machine has a name like inferencemachine.local on my home network so the Ollama URL looks like http://inference machine:11434/v1 to connect to any model I've downloaded.
> AI agent on my phone I can long-press power button and give spoken commands ("add milk to the shopping list"). Uses private home inference machine, see below.
For this part, are you using a tool-calling harness like Pi or Codex? Or did you sort of hack it together with prompts that tell it what json to emit?
I just got the rest of the “application layer” for my setup working yesterday, with a small set of evals. Auto-filing voice notes is what’s next for me.
My exact setup. Main repo on a second internal disk, one replica on an external disk, second replica in backblaze. Replicas are kept in sync with `restic copy`. Backup integrity gets checked automatically with `restic check`. It all works great.
It absolutely is primarily about preventing people from learning about the world. You can’t run a system like China’s without controlling information. During the political meetings, they ramp up their blocking, and then they usually turn it down again after.
During the World Cup (2022, still zero covid in China), they started blurring out the crowd because people were noticing that nobody in the stands was wearing masks. They’d been told that the zero covid policy and draconian lockdowns were keeping them safe, and outside China was a Covid hell-hole. Protests followed four months later.
Nobody in China was told about western covid vaccines, much less allowed to get them.
VPNs aren’t widely used — there was a study posted here some months ago that estimated VPN use at around 1% of the population, too little to matter.
That’s why they’re a bit lax. They can afford to let some through to grease the wheels of commerce. You do have to be seriously unlucky to get into trouble.
(I was there during Covid, and some years before and after)
Do you write anywhere about your time there during covid? Seeing a foreigner's perspective during that time would be fascinating.
That's some interesting info anyways if not. It's funny that the absolute number of VPN users is large but negligible compared to the overall population.
Not publicly unfortunately. I still go back to visit from time to time, and some of the things I could write about would definitely get me harassed if the wrong person found it. That's self-censorship for you.
TL;DR: it was far better than the rest of the world in 2020, marginally better in 2021, but 2022 was a shit show. I still remember Dec 7 as the day zero covid ended.
Thanks! I went so far with it that I was honestly questioning my own sanity.
The HAL has a virtualized CPU, and I spent more time than I’d care to admit precisely timing instructions on various period-accurate hardware (386SX, 486DX). I even tuned it to the point where programs that take advantage of it actually run faster on the 486 because of the built‑in math coprocessor.
> Writing directly to VRAM? WAIT for vsync?
All screen modes are supported including the ability to draw to hidden pages. It’s got a fully emulated VGA hardware layer and even a synthetic VGA beam clock, so you can do tricks like `WAIT &H3DA, 8, 8` for vertical retrace to minimize flicker.
> Call absolute for mouse usage?
Yup! Int 33h is fully supported, we basically use a virtual TSR driver which is pointed to by the interrupt vector table. I actually tested it with an old pixel art editor I made in the 90s!
PEEK/POKE and much of the BIOS are fully simulated, so you can use more advanced QuickBasic 4.5 features like calling interrupts (including silly stuff like rebooting the computer via int 19h).
There's a ton more (including a Hayes compatible modem plugged into COM1) as well.
I basically dug out a stack of my old PC books from the late ’80s and early ’90s, and they’ve been my bibles for the past several months (Undocumented DOS, The Programmer’s PC Sourcebook, etc.).
It’s about 99% done at this point. I’m hoping to do a Show HN in the next couple of weeks.
Wow, I didn’t expect this kind of reply at all. What a labor of love. Can’t wait to try it out! What made you decide to emulate things at this level instead of using a more off the shelf hardware stack?
So I wanted to build more than just a simple online QuickBasic simulator - I've seen a few of them but they all kind of fall apart at the last mile.
You really can't create a QuickBasic interpreter with any expectation of accuracy unless you also flesh out the corresponding hardware that would have accompanied it back in the day.
What I’m really aiming for is to recreate the world we grew up with as kids in the late ’80s and ’90s. I want to tap into that feeling of discovering QuickBASIC on a computer for the first time and realizing you could bring your own creations to life.
For me, and I bet a lot of kids back then, QuickBASIC was the closest thing to sorcery: you could conjure whatever was in your imagination and watch it traced out pixel by pixel on your 14-inch VGA monitor.
But I’m using my own “IDE” inspired by herdr and pane, worktrees down the left and panes on the right, but besides terminals the types of panes also include:
- A native Obsidian-level markdown editor with support for comments that agents can see - Claude code with chrome for context size, and a custom UI that looks more like the web - A diff viewer with support for comments - A browser - Can tag worktrees with PRs and issues - Everything (except the browser) works seamlessly over ssh
It’s all zig+gtk, all vibe coded. I rarely open vscode these days.
Maybe the herdr plugin ecosystem can support all this too. I kinda want to get out of the business of hand-polishing UI.
reply